I found the following description in the PeopleSemSegnet explanatory documentation.
The model is intended for training using TAO Toolkit with the user’s own dataset or using it as it is. This can provide high fidelity models that are adapted to the use case. The Jupyter notebook available as a part of TAO container can be used to re-train.
However, I could not find an official Jupyter notebook with a pre-trained PeopleSemSegnet.
Where can I find the official Jupyter notebook with pre-trained PeopleSemSegnet?
The PeopleSemSegnet is based on Unet. You can find the Unet notebook when you download notebook via below commands mentioned in TAO Toolkit Quick Start Guide - NVIDIA Docs.